Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    various forms of the word "capture."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    venir
    -0.16
    iat
    -0.14
    rew
    -0.14
    estar
    -0.14
    wyn
    -0.14
    uten
    -0.14
    oted
    -0.14
    elp
    -0.13
    403
    -0.13
    437
    -0.13
    POSITIVE LOGITS
     essence
    0.22
     attention
    0.19
    TURE
    0.18
     Catch
    0.18
     Capture
    0.17
    Catch
    0.16
    /loose
    0.16
    عات
    0.16
    grab
    0.15
    .capture
    0.15
    Act Density 0.026%

    No Known Activations